# nace-ai/kapitsa

> Apple Silicon optimized inference engine for Qwen and Nemotron models with OpenAI- and Anthropic-compatible APIs. Runs local LLMs on Mac via CLI and a web chat.

- Magnitude: 4.6 out of 10 — Early signal
- Stars: 114 total · +9 stars measured 2026-10-19, 05:36–07:43 UTC, ≈ 65 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: Apache-2.0 · Created: 2026-10-16 · Last push: 2026-10-19
- GitHub: https://github.com/nace-ai/kapitsa · Page: https://gitnova.dev/en/r/nace-ai/kapitsa

## Useful for

- Start a local OpenAI-compatible API on Mac with kapitsa serve
- Point Claude Code or Codex CLI at a local model via kapitsa claude
- Benchmark inference speed on your Mac with kapitsa bench --submit

## Why it’s here

- Star-counter measurements on 2026-10-19 (UTC), 05:36–07:43: 105 → 114 stars (+9). This is the change over that interval.
- Estimated end-of-day forecast: about +65 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 114 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #165.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 82
- Watchers: 0
- Average over the last week: 44 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2
- Latest release: v0.1.37 (2026-10-19)

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-10-16 … 2026-10-19: 0, 2, 111, 9

## Spotted in now

- Top new repositories this week: #165

## Similar by description

1. **mw00/project-maya** — 2.2 · Cooling · Language models · C++ · +17 stars measured 2026-10-19, 00:09–07:47 UTC, ≈ 43 by evening
   Local engine, server and dashboard to run the 321B MoE model GLM-5.3-Flash on one or two NVIDIA GPUs, offloading experts to RAM and NVMe.
   Full card: https://gitnova.dev/en/r/mw00/project-maya.md
2. **incoai/splash** — 1.9 · Steady · Language models · C++ · +3 stars measured 2026-10-19, 00:11–07:49 UTC, ≈ 18 by evening
   A local LLM inference engine for Apple silicon, specialized per model: serves OpenAI- and Anthropic-compatible APIs to coding agents on a single Mac.
   Full card: https://gitnova.dev/en/r/incoai/splash.md
3. **ggml-org/llama.cpp** — 3.3 · Steady · Language models · C++ · +25 stars measured 2026-10-19, 00:07–07:45 UTC, ≈ 95 by evening
   LLM and VLM inference implemented in C/C++ with no dependencies, running on CPUs and GPUs across many hardware backends. Enables local model execution with minimal setup and quantization.
   Full card: https://gitnova.dev/en/r/ggml-org/llama.cpp.md
4. **lithos-ai/lithos-metal** — 1.9 · Steady · Language models · Python · +3 stars measured 2026-10-19, 00:09–07:49 UTC, ≈ 10 by evening
   Open-source LLM inference engine for Apple silicon that compiles Metal megakernels and runs a local server with DSpark speculative decoding.
   Full card: https://gitnova.dev/en/r/lithos-ai/lithos-metal.md
5. **prabanta-dev/janas** — 2.2 · Cooling · Language models · C · +5 stars measured 2026-10-19, 00:11–07:47 UTC, ≈ 13 by evening
   Janas is a family of AI tools in C with no dependencies. Janas-LLM runs large MoE models (up to 80B, 48 GB) on a 32 GB laptop by streaming experts from NVMe SSD, and outperforms llama.cpp on all 13 tested models.
   Full card: https://gitnova.dev/en/r/prabanta-dev/janas.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-19 07:55 UTC, updated every 30 minutes.